Python数据分析

文章目录

• 加载文件夹内所有Excel数据

• 提取Excel表格中指定列数据

• 定向筛选所需数据

• 多表数据合并功能

• 多表数据统计排行

• 生成成绩分析图表 

一、加载文件夹内所有Excel数据

def get_files_name():          
    file_list = os.listdir('C:/data')
    return file_list

二、提取Excel表格中指定列数据

def get_specified_data(dictory, operation, col_name, value):
    new_dict = {}
    if col_name != "省市":
        for key in dictory.keys():
            value = float(value)
            flag = 0
            if operation == '>':
                if dictory[key][col_name] > value:
                    flag = 1
            elif operation == '>=':
                if dictory[key][col_name] >= value:
                    flag = 1
            elif operation == '=':
                if dictory[key][col_name] == value:
                    flag = 1
            elif operation == '<=':
                if dictory[key][col_name] <= value:
                    flag = 1
            elif operation == '<':
                if dictory[key][col_name] < value:
                    flag = 1
            else:
                flag = 0
            if flag == 1:
                new_dict[key] = {}
                new_dict[key] = dictory[key]
    else:
        for key in dictory.keys():
            flag = 0
            if operation == '>':
                if key > value:
                    flag = 1
            elif operation == '>=':
                if key >= value:
                    flag = 1
            elif operation == '=':
                if key == value:
                    flag = 1
            elif operation == '<=':
                if key <= value:
                    flag = 1
            elif operation == '<':
                if key < value:
                    flag = 1
            else:
                flag = 0
            if flag == 1:
                new_dict[key] = {}
                new_dict[key] = dictory[key]
    return new_dict

三、定向筛选所需数据

def show_data(dictory):
    try:
        keys = list(dictory[list(dictory.keys())[0]].keys())
    except:
        print("当前数据为空")
        return
    head = ['区域']
    head.extend(keys)
    table = PrettyTable(head)
    for key in dictory.keys():
        line = [key]
        for key_2 in keys:
            line.append(dictory[key][key_2])
        table.add_row(line)
    print(table)

四、多表数据合并功能

def save(dictory):
    name = input("文件名：")
    book = xlwt.Workbook()
    sheet = book.add_sheet('Sheet1', cell_overwrite_ok=True)
    keys = list(data[list(data.keys())[0]].keys())
    head = ["区域"]
    head.extend(keys)
    for h in range(len(head)):
        sheet.write(0, h, head[h])
    cities = list(dictory.keys())
    for city in range(len(cities)):
        sheet.write(city + 1, 0, cities[city])
        for key in range(len(keys)):
            sheet.write(city + 1, key + 1, dictory[cities[city]][keys[key]])
    book.save('C:/data/' + name + '.xls')
    print("保存成功"

五、多表数据统计排行

def sort_data(dictory, key, reverse):
    data = dictory
    if not reverse:
        data = dict(sorted(data.items(), key=lambda d: d[1][key], reverse=False))  # 字典的升序
    else:
        data = dict(sorted(data.items(), key=lambda d: d[1][key], reverse=True))  # 字典的降序
    return data

六、生成成绩分析图表

def draw_plot(dictory):
    font = {'family': 'MicroSoft Yahei', 'weight': 'normal', 'size': 10}
    matplotlib.rc('font', **font)
    index = numpy.arange(len(dictory.keys()))
    color = [(150/ 256, 75/ 256, 150/ 256,0.5),(100/ 256, 150/ 256, 100/ 256,0.5),
             (0/360, 120/360,130/360,0.5),(0,0,0,0.5)]
    first_key = list(dictory.keys())
    first_key = first_key[0]
    cols = list(dictory[first_key].keys())
    data = []
    for i in range(len(cols)):
        data.append([])
    for key in dictory.keys():
        for col in range(len(cols)):
            data[col].append(dictory[key][cols[col]])
    offset = -1 / 4
    for i in range(len(cols)):
        plt.bar(index + offset, data[i], color=color[i], width=1 / 4)
        offset += 1 / 4
    plt.xticks(index, dictory.keys())
    plt.legend(cols)
    plt.show()